List your company
ResearchFormerly WizWand

Goal-conditioned Reinforcement Learning on AntMaze Stitch Large

88Success RateEik-HiQRL
-3.5220.244467.76Jun 11, 2025Jul 11, 2025Aug 11, 2025Sep 11, 2025Oct 11, 2025Nov 11, 2025Dec 12, 2025
Updated 6mo ago

Evaluation results

MethodLinks
Eik-HiQRL2025.1288
Eik-HIQL2025.1284
HIQL2025.1274
TD-SRAction-conditioning=true2025.0629
BYOL-γAction-conditioning=true2025.0626
BYOLAction-conditioning=false2025.0626
QRL2025.1224
GCBCAction-conditioning=false2025.0624
TD-SRAction-conditioning=true2025.0623
BYOL-γAction-conditioning=true2025.0619
GCIVLAction-conditioning=false2025.0618
QRLAction-conditioning=false2025.0618
BYOLAction-conditioning=false2025.0617
TRAAction-conditioning=false2025.0617
CRL2025.1213
TRAAction-conditioning=false2025.0611
CRLAction-conditioning=false2025.0611
CRLAction-conditioning=false2025.0611
GCIQLAction-conditioning=false2025.067
GCBCAction-conditioning=false2025.063
GCIVLAction-conditioning=false2025.061
QRLAction-conditioning=false2025.061
GCIQLAction-conditioning=false2025.060